{"id":"https://openalex.org/W3008911072","doi":"https://doi.org/10.1109/icassp40776.2020.9054036","title":"Text-Independent Speaker Verification with Adversarial Learning on Short Utterances","display_name":"Text-Independent Speaker Verification with Adversarial Learning on Short Utterances","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3008911072","doi":"https://doi.org/10.1109/icassp40776.2020.9054036","mag":"3008911072"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100399798","display_name":"Kai Liu","orcid":"https://orcid.org/0000-0001-5951-2164"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kai Liu","raw_affiliation_strings":["Artificial Intelligence Application Research Center, Huawei Technologies, Shenzhen, PRC"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Application Research Center, Huawei Technologies, Shenzhen, PRC","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101911637","display_name":"Huan Zhou","orcid":"https://orcid.org/0000-0002-8251-8158"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Zhou","raw_affiliation_strings":["Artificial Intelligence Application Research Center, Huawei Technologies, Shenzhen, PRC"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Application Research Center, Huawei Technologies, Shenzhen, PRC","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100399798"],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":1.4582,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85505798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6569","last_page":"6573"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.8106987476348877},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.8083749413490295},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7964616417884827},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7516084313392639},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5207364559173584},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.47594618797302246},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.46226632595062256},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.44260355830192566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41275596618652344},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.19723418354988098}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.8106987476348877},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8083749413490295},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7964616417884827},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516084313392639},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5207364559173584},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.47594618797302246},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.46226632595062256},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.44260355830192566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41275596618652344},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.19723418354988098},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2099471712","https://openalex.org/W2121812409","https://openalex.org/W2125389028","https://openalex.org/W2150769028","https://openalex.org/W2336335760","https://openalex.org/W2395750323","https://openalex.org/W2517529173","https://openalex.org/W2520774990","https://openalex.org/W2746742816","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W2795804790","https://openalex.org/W2801581493","https://openalex.org/W2888897023","https://openalex.org/W2889052710","https://openalex.org/W2898213692","https://openalex.org/W2916104401","https://openalex.org/W2963865582","https://openalex.org/W2963981733","https://openalex.org/W2973099347","https://openalex.org/W3008104819","https://openalex.org/W4301206121","https://openalex.org/W4320013936","https://openalex.org/W6678815747","https://openalex.org/W6755827578","https://openalex.org/W6779669310"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W2529301793","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W2384121599","https://openalex.org/W1998549096","https://openalex.org/W2767892728","https://openalex.org/W4312095835","https://openalex.org/W1996621592"],"abstract_inverted_index":{"A":[0],"text-independent":[1],"speaker":[2,70],"verification":[3,71,111],"system":[4],"suffers":[5],"severe":[6],"performance":[7,112],"degradation":[8],"under":[9],"short":[10,32,149],"utterance":[11],"condition.":[12],"To":[13],"address":[14],"the":[15,69,88,110,132,145],"problem,":[16],"in":[17,82,144],"this":[18,83],"paper,":[19],"we":[20],"propose":[21],"an":[22,35],"adversarially":[23],"learned":[24],"embedding":[25,33,37],"mapping":[26],"model":[27],"that":[28,104],"directly":[29],"maps":[30],"a":[31,43,47,119],"to":[34,86,109],"enhanced":[36],"with":[38,46,122,134],"increased":[39],"discriminability.":[40],"In":[41],"particular,":[42],"Wasserstein":[44,120],"GAN":[45,121],"bunch":[48],"of":[49,63,90,148],"loss":[50,55,92,124],"criteria":[51,93,106],"are":[52,65,107],"investigated.":[53],"These":[54],"functions":[56],"have":[57,115],"distinct":[58],"optimization":[59],"objectives":[60],"and":[61,140],"some":[62,105,114],"them":[64],"less":[66],"favoured":[67],"for":[68],"research":[72],"area.":[73],"Different":[74],"from":[75],"most":[76],"prior":[77],"studies,":[78],"our":[79],"main":[80],"objective":[81],"study":[84],"is":[85],"investigate":[87],"effectiveness":[89],"those":[91],"by":[94],"conducting":[95],"numerous":[96],"ablation":[97],"studies.":[98],"Experiments":[99],"on":[100,138,142],"Voxceleb":[101],"dataset":[102],"showed":[103],"beneficial":[108],"while":[113],"trivial":[116],"effects.":[117],"Lastly,":[118],"chosen":[123],"criteria,":[125],"without":[126],"finetuning,":[127],"achieves":[128],"meaningful":[129],"advancements":[130],"over":[131],"baseline,":[133],"4%":[135],"relative":[136],"improvements":[137],"EER":[139],"7%":[141],"minDCF":[143],"challenging":[146],"scenario":[147],"2second":[150],"utterances.":[151]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}